WO2016027410A1 - Detection device and detection system - Google Patents

Detection device and detection system Download PDF

Info

Publication number
WO2016027410A1
WO2016027410A1 PCT/JP2015/003586 JP2015003586W WO2016027410A1 WO 2016027410 A1 WO2016027410 A1 WO 2016027410A1 JP 2015003586 W JP2015003586 W JP 2015003586W WO 2016027410 A1 WO2016027410 A1 WO 2016027410A1
Authority
WO
WIPO (PCT)
Prior art keywords
person
detection
amount
unit
detection mode
Prior art date
Application number
PCT/JP2015/003586
Other languages
French (fr)
Japanese (ja)
Inventor
康洋 森
松田　啓史
利春 竹ノ内
杭　耕一郎
Original Assignee
パナソニックＩｐマネジメント株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by パナソニックＩｐマネジメント株式会社 filed Critical パナソニックＩｐマネジメント株式会社
Publication of WO2016027410A1 publication Critical patent/WO2016027410A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18—Status alarms
    • G08B21/22—Status alarms responsive to presence or absence of persons
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Definitions

  • the present invention relates to a detection device and a detection system.
  • Patent Document 1 when the intruder moves little or stays within the detection region, the image described in Patent Document 1 is recognized as a disturbance because the area of the image movement due to the intruder movement is reduced. End up. Therefore, the thing of patent document 1 has a problem that an intruder cannot be detected when the intruder moves little or stays in the detection area.
  • the device described in Patent Document 2 always detects the presence or absence of a detection target by repeating the first contour extraction means to the third contour extraction means. For example, when the detection target moves greatly. First, it is determined whether or not the detection target is stationary, and after determining whether or not the object is moving slightly, it is determined whether or not the object is moving greatly, so the load on the detection process Is big.
  • the present invention has been made in view of the above-described reasons, and a detection device that can detect the presence / absence of a person with high accuracy according to the movement state of the person with a small load on the detection process and
  • the purpose is to provide a detection system.
  • the detection unit that detects the presence of a person in the region of the analysis image captured by the imaging unit, and the detection unit A creation unit that creates an identification region that surrounds the detected person, and a derivation unit that derives the amount of movement of the person and the position change amount of the identification region, and the detection unit detects the presence of the person in the region of the analysis image.
  • the position change amount is less than a first threshold value.
  • the entry detection mode is switched to the stay detection mode.
  • the stay detection mode when the amount of movement of the person is equal to or greater than the second threshold, the stay detection mode is switched to the entry detection mode.
  • the detection system detects that there is a person in the area of the analysis image, and a detection unit that detects the presence or absence of a person in the area of the analysis image captured by the imaging unit
  • a control unit based on the detection result of the presence or absence of a person by the detection unit, a creation unit that creates an identification region surrounding the detected person, a derivation unit that derives the amount of movement of the person and the position change amount of the identification region
  • a detection unit having a transmission unit that transmits to a control target, and a load to be controlled. The detection unit detects an presence of a person in the region of the analysis image, and an identification region.
  • a stay detection mode that detects the presence or absence of a person based on the amount of movement of the person in the case, and in the approach detection mode, when the position change amount is less than the first threshold, the mode is switched from the approach detection mode to the stay detection mode.
  • the stay detection mode Te when the motion amount of the human is equal to or greater than the second threshold value, and switches from staying detection mode to enter the detection mode.
  • the detection device and the detection system have a small load on the detection process, and can accurately detect the presence or absence of a person according to the movement situation of the person.
  • FIG. 1 is a block diagram of a detection system according to the first embodiment.
  • FIG. 2 is a conceptual diagram illustrating an example of an identification region created by the creation unit of the detection apparatus according to the first embodiment for an analysis image, and an example of a derivation unit deriving a positional change amount of the identification region.
  • A) is a conceptual diagram which shows the area
  • (B) is a conceptual diagram showing a region of an analysis image in a frame after two consecutive frames of the analysis image.
  • FIG. 3 is a conceptual diagram illustrating an example in which the deriving unit derives the amount of human movement when the detection device according to the first embodiment detects the presence or absence of a person in the stay detection mode.
  • FIG. 4 is a flowchart in which the detection apparatus according to the first embodiment of the present invention switches the detection mode based on the position change amount of the identification area.
  • FIG. 5 is a flowchart in which the detection device according to the first embodiment detects the presence or absence of a person in the approach detection mode.
  • FIG. 6 is a flowchart in which the detection device according to the first embodiment detects the presence or absence of a person in the stay detection mode.
  • FIG. 7 is a block diagram of a detection system according to the second embodiment.
  • FIG. 8 is a conceptual diagram illustrating an example of filtered image processing according to the second embodiment.
  • FIG. 9 is a flowchart in which the detection device according to the second embodiment detects the presence or absence of a person in the stay detection mode.
  • FIG. 1 is a block diagram of a detection system 120 according to the first embodiment.
  • the detection system 120 includes a detection device 100 and a load 6.
  • the detection apparatus 100 includes an imaging unit 2, a control unit 3, a transmission unit 4 that transmits a control signal to a control target in accordance with the presence or absence of a person, and a storage unit 5.
  • the control unit 3 detects the presence or absence of a person in the area of the analysis image captured by the imaging unit 2, and when the detection unit 31 detects the presence of a person in the area of the analysis image A creating unit 32 that creates an identification region surrounding the detected person, and a deriving unit 33 that derives the amount of movement of the person and the position change amount of the identification region.
  • the deriving unit 33 derives the amount of human movement during a predetermined period.
  • the deriving unit 33 derives the position change amount of the identification area in a predetermined period.
  • the above-mentioned “predetermined period” will be described as a frame interval between two consecutive frames of the analysis image captured by the imaging unit 2, but the present invention is not limited thereto, and for example, a preset period may be used.
  • the predetermined period for deriving the amount of human movement in the identification area and the predetermined period for deriving the position change amount of the identification area may be the same period or different periods.
  • the storage unit 5 stores a change amount threshold value I as an evaluation index, a motion amount threshold value U, a stay detection threshold value T smaller than the motion amount threshold value U, and a luminance change amount threshold value K.
  • the threshold values I, U, T, and K may be referred to as first, second, third, and fourth threshold values, respectively.
  • the detection unit 31 includes, as detection modes, an entry detection mode that detects the presence / absence of a person in the area of the analysis image, a stay detection mode that detects the presence / absence of a person based on the amount of movement of the person in the identification area, Have
  • the detection method of the presence or absence of a person in the approach detection mode of the detection unit 31 is not particularly limited, and a conventional human detection technique may be used.
  • a technique for detecting the presence or absence of a person using background difference may be used, or a technique for detecting the presence or absence of a person by deriving the amount of movement of the person in the region 21 of the analysis image using a difference between frames. Good.
  • FIG. 2 is a conceptual diagram showing an example of the identification region 22 created by the creation unit 32 and an example of the derivation unit 33 deriving the positional change amount of the identification region 22.
  • FIGS. 2A and 2B are diagrams showing an analysis image region 21 of two consecutive frames.
  • the creation unit 32 identifies the rectangle based on the width and height of the person. A region 22 is created so as to surround the person.
  • FIG. 2 (b) shows the next frame of FIG. 2 (a).
  • the identification area 22 is shown in FIG. 2 (a).
  • the identification area 22a moves to the identification area 22b in FIG. 2b.
  • the deriving unit 33 calculates the distance A between the center of the identification area 22a and the center of 22b, and derives the distance A as a position change amount of the identification area 22.
  • the detection unit 31 compares the position change amount derived by the deriving unit 33 with the threshold value I of the change amount stored in the storage unit 5 (that is, the first threshold value). When the change amount is equal to or greater than the threshold value I, the presence / absence of a person is detected in the approach detection mode.
  • the creation unit 32 updates the position of the identification region 22 as the person moves within the analysis image region of the detection apparatus 100, so that the detection unit can track the person within the analysis image region.
  • FIG. 3 is a conceptual diagram illustrating an example in which the deriving unit 33 derives the amount of human movement when the detection apparatus 100 detects the presence or absence of a person in the stay detection mode.
  • FIGS. 3A and 3B are diagrams showing identification regions 22c and 22d of two consecutive frames.
  • the detection unit 31 detects the presence or absence of a person based on the amount of movement of the person in the identification area 22. As shown in FIG. 3, when the movement of a person changes from the identification area 22c in FIG. 3A to the identification area 22d in FIG. 3B, the luminance of the pixel changes due to fluctuations in the movement of the person. Change based on.
  • the deriving unit 33 derives the amount of human movement in the identification area 22 during a predetermined period. That is, the deriving unit 33 counts the number of pixels in which the luminance change amount of the pixel between the identification region 22c and the identification region 22d is equal to or larger than the threshold value K (that is, the fourth threshold value) of the luminance change amount stored in the storage unit 5. , Is derived as the amount of human movement.
  • the detection unit 31 derives the amount of movement of the person by the deriving unit 33, so that the amount of movement of the person and the threshold T of stay detection stored in the storage unit 5 (that is, the third threshold) , The threshold U of motion amount (that is, the second threshold) is compared.
  • the detection unit 31 determines that there is a person if the amount of movement of the person is greater than or equal to the threshold T and less than the threshold U. Moreover, if the amount of movement of the person is less than the threshold value T, the detection unit 31 determines that there is no person.
  • the detection part 31 will switch from stay detection mode to approach detection mode, if the amount of human movement is more than the threshold value U.
  • the load 6 is a lighting device having at least two operation modes of “turned on” and “turned off”.
  • the transmission unit 4 transmits a control signal that is lit to the load 6 to be controlled outside the detection apparatus 100. To do.
  • the transmission unit 4 transmits a control signal for switching to the “lights off” operation mode when the detection unit 31 determines that no person is present. To do.
  • the transmission part 4 may transmit a control signal directly with respect to the load 6, and may transmit a control signal indirectly via a repeater (not shown) etc.
  • the communication method of the transmission unit 4 may be, for example, a wireless communication method using Wi-Fi (Wireless Fidelity, registered trademark) or a wired communication method using a signal line, but is not particularly limited.
  • Wi-Fi Wireless Fidelity, registered trademark
  • wired communication method using a signal line but is not particularly limited.
  • FIG. 4 is a flowchart in which the detection device 100 switches the detection mode based on the position change amount of the identification region 22.
  • the detection unit 31 Before the person enters the area of the analysis image captured by the imaging unit 2 of the detection apparatus 100, the detection unit 31 detects the presence or absence of a person in the entry detection mode (step S41). Therefore, when detecting the presence of a person in the area of the analysis image, the detecting unit 31 detects the position change amount of the identification region 22 derived by the deriving unit 33 and the change amount threshold I (that is, the first value). (Threshold) is compared (step S42).
  • step S42 If the position change amount of the identification area 22 is less than I (NO in step S42), the detection unit 31 proceeds to step S43 and switches the detection mode from the entry detection mode to the stay detection mode. If the position change amount of the identification region 22 is I or more (YES in step S42), the detection unit 31 returns to step S41 and continues to detect the presence or absence of a person in the approach detection mode.
  • step S43 the detection unit 31 detects the presence or absence of a person in the stay detection mode. Therefore, the detection unit 31 compares the human motion amount derived by the deriving unit 33 with the motion amount threshold value U (that is, the second threshold value) (step S44).
  • the detection unit 31 continues to detect the presence or absence of the person in the stay detection mode. Otherwise, that is, if the amount of human movement is greater than or equal to U (NO in step S44), the detection unit 31 returns to step S41 and switches the detection mode from the stay detection mode to the entry detection mode.
  • FIG. 5 is a flowchart in which the detection device 100 detects the presence or absence of a person in the approach detection mode.
  • step S51 the detection unit 31 detects the presence or absence of a person based on the analysis image captured by the imaging unit 2. Therefore, when the detection unit 31 detects that a person is present in the area of the analysis image (YES in step S52), the creation unit 32 creates the identification region 22 (step S53).
  • step S52 when detecting that there is no person, the detection unit 31 returns to step S51 and subsequently detects the presence or absence of the person in the entry detection mode.
  • step S54 the detection unit 31 compares the position change amount of the identification area 22 derived by the deriving unit 33 with the change amount threshold value I (that is, the first threshold value).
  • step S54 If the position change amount is I or more (YES in step S54), the detection unit 31 returns to step S51, and subsequently detects the presence or absence of a person in the entry detection mode. If the amount of change in position is less than I (NO in step S54), detection unit 31 switches the detection mode from the entry detection mode to the stay detection mode (step S55), and detects the presence or absence of a person in the stay detection mode. . As described above, step S54 is substantially the same as step S42.
  • FIG. 6 is a flowchart in which the detection apparatus 100 detects the presence or absence of a person in the stay detection mode.
  • step S61 the detection unit 31 detects the presence or absence of a person based on the analysis image in the identification region 22. Therefore, the detection unit 31 compares the amount of movement of the person derived by the deriving unit 33 with the threshold value T (that is, the third threshold value) for stay detection (step S62).
  • the detection unit 31 determines that there is no person (step S64). If the movement amount of the person is equal to or greater than T (YES in step S62), the detection unit 31 compares the movement amount of the person with the threshold U of the movement amount (that is, the second threshold) (step S63).
  • step S63 if the amount of movement of the person is less than U (YES in step S63), the detection unit 31 determines that there is a person (step S65), and continues to check whether there is a person in the stay detection mode. Detect. If the amount of movement of the person is U or more (NO in step S63), the detection unit 31 switches the detection mode from the stay detection mode to the entry detection mode, and detects the presence or absence of a person in the entry detection mode (step S66). ).
  • the detection unit 31 When detecting the presence or absence of a person in the identification area 22 in the stay detection mode, the detection unit 31 detects the presence or absence of another person outside the identification area 22 and in the analysis image area 21 in the entry detection mode. Detect. Therefore, when a person other than the person in the identification area 22 enters the area 21 of the analysis image, the detection unit 31 can detect the presence of the person in the entry detection mode.
  • the detection system 120 includes an imaging unit 2, a detection unit 31 that detects the presence / absence of a person in an analysis image area captured by the imaging unit 2, and the detection unit 31 includes a person in the analysis image area 21.
  • the creation part 32 which creates the identification area 22 surrounding the detected person
  • the deriving part 33 for deriving the amount of movement of the person and the position change amount of the identification area 22, and the detection part 31 are the presence of the person.
  • a detection device 100 including a transmission unit 4 that transmits a control signal to a control target based on a detection result of the presence or absence of the control signal, and a load 6 that is a control target.
  • Position change amount is the threshold of change amount When it is less than I (that is, the first threshold value), the mode is switched from the approach detection mode to the stay detection mode.
  • the stay detection mode when the human motion amount is equal to or greater than the motion amount threshold value U (that is, the second threshold value) Switch from mode to entry detection mode.
  • the detection device 100 and the detection system 120 can achieve the following effects as compared with those described in Patent Document 2.
  • the image processing apparatus described in Patent Literature 2 detects a first contour extraction unit that detects a detection target when the movement amount or movement of the detection target is large, and a detection when the movement amount or movement of the detection target is relatively small. It has the 2nd outline extraction means which detects a target, and the 3rd outline extraction means which detects a detection target, when a detection target is still. However, the image processing apparatus described in Patent Document 2 always detects the presence / absence of a detection target by repeating the first contour extraction means to the third contour extraction means. For example, even if the detection target is moving greatly, the first contour extraction means does not always detect the detection target, but it is repeatedly determined whether the detection target is stationary first, and then a slight amount is detected. Since it is determined whether or not it is moving after determining whether or not it is moving, the load on the detection process is large.
  • the detection unit 31 is less than the change amount threshold I (that is, the first threshold) in the approach detection mode.
  • the change amount threshold I that is, the first threshold
  • the detection unit switches from the stay detection mode to the entry detection mode. Detect the presence or absence of. Therefore, since the amount of processing by the image processing apparatus described in Patent Document 2 is small, the load on the detection process is small.
  • the detection device 100 and the detection system 120 have a small load on the detection process, and can accurately detect the presence or absence of a person according to a person's action.
  • the detection unit 31 of the detection device 100 and the detection system 120 detects a person whose movement amount is relatively small or stays in the stay detection mode, the presence of a person based on the analysis image in the identification region 22 is detected. Even if there is a disturbance outside the area of the identification area 22, for example, when an animal such as a bird or a cat enters the detection range, or when reflected light from a switch or a mirror is generated, Without being affected, it is possible to detect the presence or absence of a person whose movement amount is relatively small or staying.
  • the deriving unit 33 derives the number of pixels in which the luminance change amount of the pixels in the identification region 22 between frames is equal to or greater than the luminance change amount threshold value K (that is, the fourth threshold value) as a human motion amount, Even if a pixel whose luminance change amount is less than K occurs due to a disturbance in the identification region 22, the detection unit 31 can detect the presence or absence of a person without being affected by the influence.
  • K luminance change amount threshold value
  • the detection device 100 and the detection system 120 can detect the presence or absence of a person with high accuracy and efficiency even when the movement amount of the person is relatively small or stays within the detection range.
  • the detection unit 31, the creation unit 32, and the derivation unit 33 are provided in the control unit 3, and the transmission unit 4 and the storage unit 5 are externally attached to the control unit 3. Because it is a matter, it is not limited to that.
  • the transmission unit 4 and the storage unit 5 may be provided in the control unit 3.
  • the entire image captured by the imaging unit 2 is not limited to the analysis image region, and for example, a part of the image captured by the imaging unit 2 may be used as the analysis image region.
  • the load 6 is not limited to the lighting device, and may be an electric device having at least two operation modes such as an air conditioner and a cooking device.
  • the frame interval of the imaging unit 2 that is, the period between FIG. 2a and FIG. 2b and the period between FIG. 3a and FIG. 3b are, for example, 200 ms, but are not limited thereto.
  • the deriving unit 33 derives the amount of change in the position of the identification region 22, the deriving unit 33 is not necessarily limited to using the center of the identification region 22 as a reference point.
  • the transmission unit 4 transmits different control signals to the load 6 when the detection unit 31 determines that there is a person in the stay detection mode and when it is determined that there is a person in the approach detection mode. May be. By doing so, the load 6 can be controlled according to the person's approach and stay.
  • the detection device 200 and the detection system 220 according to the second embodiment will be described with reference to FIGS.
  • the detection system 220 has a point that the control unit 3 further includes an image processing unit 34 that performs image processing on the analysis image, and the detection unit 31 continuously operates over a predetermined period Q in the stay mode. It is different in that it is determined that there is no person when it is detected that there is no person.
  • symbol is attached
  • FIG. 7 is a block diagram of the detection system 220 according to the second embodiment.
  • the detection system 220 includes a detection device 200 and a load 6.
  • the control unit 3 of the detection device 200 further includes an image processing unit 34.
  • the storage unit 5 further stores a threshold value Q for the period.
  • the image processing unit 34 performs Sobel filter image processing on the analysis image captured from the imaging unit 2.
  • the image processing unit 34 performs Sobel filter image processing on the analysis image, and outputs the output image after the image processing to the detection unit 31, the creation unit 32, and the derivation unit 33.
  • FIG. 8 is a conceptual diagram showing an example of an analysis image picked up from the image pickup unit 2 and an output image after the Sobel filter image processing is applied to the analysis image.
  • the outline of the person to be detected can be detected with higher accuracy.
  • FIG. 9 is a flowchart in which the detection device 200 detects the presence or absence of a person in the stay detection mode.
  • step S91 the detection unit 31 acquires an output image obtained by applying the Sobel filter image processing to the analysis image by the image processing unit 34, and the human motion amount in the identification region Detect presence or absence.
  • step S92 the detection unit 31 compares the amount of movement of the person in the identification area 22 derived by the deriving unit 33 with the threshold value T for stay detection. If the human motion amount is equal to or greater than the threshold T (YES in step S92), the detection unit 31 compares the human motion amount with the motion amount threshold U (step S95). If the amount of human movement is less than the threshold T (NO in step S92), the detection unit 31 starts time counting and determines whether or not the period threshold Q has elapsed (step S93).
  • step S93 the detection unit 31 determines that there is no person when the amount of movement of the person is continuously less than the threshold T during the designated period Q (YES in step S93) (step S94). Otherwise, the detection unit 31 resets the time count and continuously detects the presence or absence of a person in the stay detection mode (NO in step S93).
  • step S95 if the amount of movement of the person is less than U (YES in step S95), the detection unit 31 determines that there is a person (step S96) and continues to track the person in the stay detection mode. If the movement amount of the person is U or more (NO in step S95), the detection unit 31 switches the detection mode from the stay detection mode to the entry detection mode (step S97).
  • the detection device 200 and the detection system 220 can detect the presence or absence of a person with higher accuracy by applying the Sobel filter image processing to the analysis image by the image processing unit 34.
  • the detection unit 31 is described as detecting the presence / absence of a person based on an output image to which filter image processing is applied when detecting the presence / absence of a person in the stay detection mode, the present invention is not limited thereto.
  • An output image to which filter image processing is applied may also be used when detecting the presence or absence of a person in the entry detection mode.
  • the filter image processing is not limited to the Sobel filter image processing.
  • a primary differential filter for example, edge detection, line detection, etc.
  • a secondary differential filter for example, Laplacian filter, etc.
  • image enhancement for example, , Low frequency enhancement, high frequency enhancement, etc.
  • image processing unit 34 is not limited to that provided in the control unit 3.
  • it may be provided separately from the control unit 3.
  • the presence or absence of a person in the stay mode is detected with higher accuracy by determining that there is no person when the detection unit 31 detects that there is no person continuously over the predetermined period Q in the stay mode. can do.
  • control unit 3 has an image processing unit 34 that performs image processing on the analysis image, and that the presence of a person is detected when the detection unit 31 detects that no person exists continuously over a predetermined period Q in the stay mode.
  • the point determined to be not limited is not limited to the point that is used together, but only one of them may be used.
  • the detection system 320 includes the number of pixels in which the luminance change amount of the pixels in the identification area 22 in the stay detection mode is greater than or equal to the threshold K of the luminance change amount and the identification area.
  • the ratio of the number of pixels in 22 is derived as the amount of human movement, and in the approach detection mode, the number of pixels in which the luminance change amount in the analysis image area 21 is equal to or greater than the threshold value K of the luminance change amount and the analysis image
  • the difference is that the ratio of the number of pixels in the area 21 is derived as the amount of human movement.
  • symbol is attached
  • the deriving unit 33 of the detection device 300 has a ratio between the number of pixels whose luminance change amount in the identification region 22 is equal to or greater than the threshold value K of the luminance change amount and the number of pixels in the identification region 22;
  • the number of pixels whose luminance change amount in the analysis image region 21 is equal to or greater than the threshold K of luminance change amount and the number of pixels in the analysis image region 21.
  • the ratio of the above and the amount of movement of the person is derived.
  • the detection unit 31 of the detection device 300 and the detection system 320 compares the amount of movement of the person derived by the deriving unit 33 with the threshold value S of the entry detection stored in the storage unit 5 in the entry detection mode, thereby Determine the presence or absence.
  • the detection unit 31 of the detection device 300 and the detection system 320 compares the amount of movement of the person derived by the deriving unit 33 with the threshold T for detection of stay in the stay detection mode, and determines whether or not a person is present.
  • the threshold value S for entering detection and the threshold value T for stay detection are not particularly limited.
  • the stay detection threshold T may be set to be smaller than the entry detection threshold S.
  • the deriving unit 33 of the detection device 300 and the detection system 320 includes the number of pixels whose luminance change amount in the identification area 22 is equal to or greater than the threshold value K of the luminance change amount and the number of pixels in the identification area 22.
  • the number of pixels whose luminance change amount in the analysis image area 21 is greater than or equal to the threshold K of the luminance change amount and the analysis image area 21 in the approach detection mode.
  • the detection system 420 is an area of a pixel block in which the luminance change amount of the pixel in the identification region 22 is greater than or equal to the threshold value K of the luminance change amount in the stay detection mode. Is calculated as the amount of human movement, and in the approach detection mode, the number of pixels whose luminance change amount in the analysis image area 21 is equal to or greater than the threshold K of the luminance change amount and the pixels in the analysis image area 21. The difference is that the area size of the lump is derived as the amount of human movement.
  • symbol is attached
  • the deriving unit 33 of the detection device 400 and the detection system 420 sets pixels adjacent to each other vertically, horizontally, or diagonally as one lump.
  • the deriving unit 33 of the detection device 400 and the detection system 420 determines the size of an area of a pixel block in which the luminance change amount of the pixel in the identification region 22 is equal to or greater than the threshold value K of the luminance change amount.
  • the size of the pixel block area in which the luminance change amount of the pixel in the region 21 of the analysis image is equal to or greater than the threshold value K of the luminance change amount is derived as the human motion amount.
  • the deriving unit 33 of the detection device 400 and the detection system 420 uses the size of the block of pixels as a reference instead of the number of the pixels in the pixel whose luminance change amount is equal to or greater than the threshold value K of the luminance change amount. As described above, by deriving the amount of human motion, the pixels whose luminance changes due to disturbance are dispersed and can be made less susceptible to the influence. Therefore, the detection device 400 and the detection system 420 can detect the presence or absence of a person with higher accuracy.
  • the detection apparatus 500 and the detection system 520 according to the fifth embodiment will be described.
  • the detection device 500 and the detection system 520, the detection device 200 and the detection system 220, and the deriving unit 33 derives the standard deviation of the luminance change amount of the pixel in the identification area 22 in the stay detection mode as the amount of human movement, The difference is that, in the detection mode, the standard deviation of the amount of change in luminance of the pixel in the region 21 of the analysis image is derived as the amount of human movement.
  • symbol is attached
  • the deriving unit 33 of the detection device 500 and the detection system 520 derives the amount of movement of the person based on the standard deviation of the change amount of the pixel luminance in the region 21 of the analysis image, so that the detection unit 31 detects the luminance of the pixel. It is possible to detect the presence / absence of a person from the difference between frames by reducing the variation in the amount of change.
  • the detection device 500 and the detection system 520 can detect the presence or absence of a person with higher accuracy.
  • the slope (variance) of the amount of change during a predetermined period with the standard deviation is used as the amount of human movement. It may be derived.
  • Detection device 120 100, 200, 300, 400, 500 Detection device 120, 220, 320, 420, 520 Detection system 2 Imaging unit 21 Analysis image regions 22, 22a, 22b, 22c, 22d Identification region 3 Control unit 31 Detection unit 32 Creation unit 33 Deriving unit 34 Image processing unit 4 Transmitting unit 5 Storage unit 6 Load

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Image Analysis (AREA)
  • Geophysics And Detection Of Objects (AREA)

Abstract

A detection device (100) is provided with an image pickup unit (2), a detection unit (31), a creation unit (32) for creating an identification area (22) that surrounds a person detected by the detection unit (31), and a derivation unit (33) for deriving an amount of movement of the person and an amount of positional change of the identification area (22), wherein the detection unit (31) has an entry detection mode for detecting existence or nonexistence of the person when the person moves and a stay detection mode for detecting existence or nonexistence of the person on the basis of the amount of movement of the person during a stay of the person. In the entry detection mode, if the amount of positional change is less than a first threshold value, the entry detection mode is switched to the stay detection mode. In the stay detection mode, if the amount of movement of the person is equal to or more than a second threshold value, the stay detection mode is switched to the entry detection mode.

Description

検知装置および検知システムDetection device and detection system
　本発明は、検知装置および検知システムに関する。 The present invention relates to a detection device and a detection system.
　従来、侵入者を検知するために、侵入者の移動に対して差分画像における像の面積を求め、外乱と区別するように侵入者の移動による像の動きの面積が一定値以上であれば、侵入者として検出する検知装置が知られている。（例えば、特許文献１を参照） Conventionally, in order to detect an intruder, the area of the image in the difference image is obtained with respect to the movement of the intruder, and if the area of the image movement due to the movement of the intruder is not less than a certain value so as to distinguish it from disturbance, Detection devices that detect as intruders are known. (For example, see Patent Document 1)
　また、検出対象の移動量や動きが大きい場合に検出対象を検出する第１の輪郭抽出手段と、検出対象の移動量や動きが比較的に小さい場合に検出対象を検出する第２の輪郭抽出手段と、検出対象が静止している場合に検出対象を検出する第３の輪郭抽出手段と、を有し、各輪郭抽出手段を用いて検知領域の大きさが異なる検知範囲において、検出対象の存在の有無を検出する複数の検出モードを備えることで、検出対象の動きが速くても、遅くても、または静止していても、検出対象を検出できる画像処理装置が知られている。（例えば、特許文献２を参照） In addition, a first contour extraction unit that detects a detection target when the movement amount and movement of the detection target are large, and a second contour extraction that detects the detection target when the movement amount and movement of the detection target are relatively small. Means and a third contour extraction means for detecting the detection target when the detection target is stationary, and in each of the detection ranges in which the size of the detection area is different using each contour extraction means, 2. Description of the Related Art An image processing apparatus that can detect a detection target regardless of whether the detection target moves fast, slow, or stationary by providing a plurality of detection modes that detect presence / absence of presence is known. (For example, see Patent Document 2)
特開２０００－３４８２６８号公報JP 2000-348268 A 特開２００４－２９５４１６号公報JP 2004-295416 A
　しかしながら、特許文献１に記載のものは、侵入者が検知領域内において移動が小さい、または滞在している場合、侵入者の移動による像の動きの面積が小さくなってしまい、外乱として認識してしまう。よって、特許文献１に記載のものは、侵入者が検知領域内において移動が小さい、または滞在している場合、侵入者を検出することができなくなるという問題がある。 However, when the intruder moves little or stays within the detection region, the image described in Patent Document 1 is recognized as a disturbance because the area of the image movement due to the intruder movement is reduced. End up. Therefore, the thing of patent document 1 has a problem that an intruder cannot be detected when the intruder moves little or stays in the detection area.
　また、特許文献２に記載のものは、常に第１の輪郭抽出手段～第３の輪郭抽出手段を繰り返して検出対象の存在の有無を検知しており、例えば、検出対象が大きな動きをするとき、先ず検出対象が静止しているか否かを判断し、ついで微少な動きをしているか否かを判断した後、大きな動きをしているか否かを判断しているため、検知処理にかかる負荷が大きい。 In addition, the device described in Patent Document 2 always detects the presence or absence of a detection target by repeating the first contour extraction means to the third contour extraction means. For example, when the detection target moves greatly. First, it is determined whether or not the detection target is stationary, and after determining whether or not the object is moving slightly, it is determined whether or not the object is moving greatly, so the load on the detection process Is big.
　そこで、本発明は、上記事由に鑑みて為されたものであって、検知処理にかかる負荷が小さく、人の移動状況に応じて人の存在の有無を精度高く検知することができる検知装置および検知システムを提供することを目的とする。 Therefore, the present invention has been made in view of the above-described reasons, and a detection device that can detect the presence / absence of a person with high accuracy according to the movement state of the person with a small load on the detection process and The purpose is to provide a detection system.
　検知装置は、撮像部と、撮像部が撮像した解析画像の領域内の人の存在の有無を検知する検知部と、検知部が解析画像の領域内に人の存在があることを検知したとき、検知した人を囲む識別領域を作成する作成部と、人の動き量および識別領域の位置変化量を導出する導出部と、を備え、検知部は、解析画像の領域内における人の存在の有無を検知する進入検知モードと、識別領域内における人の動き量で人の存在の有無を検知する滞在検知モードと、を有し、進入検知モードにおいて、位置変化量が第１の閾値未満の場合、進入検知モードから滞在検知モードに切り替え、滞在検知モードにおいて、人の動き量が第２の閾値以上の場合、滞在検知モードから進入検知モードに切り替えることを特徴とする。 When the detection device detects the presence of a person in the region of the analysis image, the detection unit that detects the presence of a person in the region of the analysis image captured by the imaging unit, and the detection unit A creation unit that creates an identification region that surrounds the detected person, and a derivation unit that derives the amount of movement of the person and the position change amount of the identification region, and the detection unit detects the presence of the person in the region of the analysis image. An entry detection mode for detecting presence / absence, and a stay detection mode for detecting the presence / absence of a person based on the amount of movement of a person in the identification area. In the entry detection mode, the position change amount is less than a first threshold value. In the case, the entry detection mode is switched to the stay detection mode. In the stay detection mode, when the amount of movement of the person is equal to or greater than the second threshold, the stay detection mode is switched to the entry detection mode.
　検知システムは、撮像部と、撮像部が撮像した解析画像の領域内の人の存在の有無を検知する検知部と、検知部が解析画像の領域内に人の存在があることを検知したとき、検知した人を囲む識別領域を作成する作成部と、人の動き量および識別領域の位置変化量を導出する導出部と、検知部による人の存在の有無の検知結果に基づいて制御信号を制御対象に送信する送信部と、を有する検知装置と、制御対象となる負荷と、を備え、検知部は、解析画像の領域内における人の存在の有無を検知する進入検知モードと、識別領域内における人の動き量で人の存在の有無を検知する滞在検知モードと、を有し、進入検知モードにおいて、位置変化量が第１の閾値未満の場合、進入検知モードから滞在検知モードに切り替え、滞在検知モードにおいて、人の動き量が第２の閾値以上の場合、滞在検知モードから進入検知モードに切り替えることを特徴とする。 When the detection system detects that there is a person in the area of the analysis image, and a detection unit that detects the presence or absence of a person in the area of the analysis image captured by the imaging unit A control unit based on the detection result of the presence or absence of a person by the detection unit, a creation unit that creates an identification region surrounding the detected person, a derivation unit that derives the amount of movement of the person and the position change amount of the identification region A detection unit having a transmission unit that transmits to a control target, and a load to be controlled. The detection unit detects an presence of a person in the region of the analysis image, and an identification region. A stay detection mode that detects the presence or absence of a person based on the amount of movement of the person in the case, and in the approach detection mode, when the position change amount is less than the first threshold, the mode is switched from the approach detection mode to the stay detection mode. In the stay detection mode Te, when the motion amount of the human is equal to or greater than the second threshold value, and switches from staying detection mode to enter the detection mode.
　検知装置および検知システムは、検知処理にかかる負荷が小さく、人の移動状況に応じて人の存在の有無を精度高く検知することができる。 The detection device and the detection system have a small load on the detection process, and can accurately detect the presence or absence of a person according to the movement situation of the person.
図１は、実施形態１に係る検知システムのブロック図である。FIG. 1 is a block diagram of a detection system according to the first embodiment. 図２は、実施形態１に係る検知装置の作成部が解析画像に対して作成する識別領域の一例と、導出部が識別領域の位置変化量を導出する一例を示す概念図である。（ａ）は、解析画像の連続する２つのフレームの前のフレームにおける解析画像の領域を示す概念図である。（ｂ）は、解析画像の連続する２つのフレームの後のフレームにおける解析画像の領域を示す概念図である。FIG. 2 is a conceptual diagram illustrating an example of an identification region created by the creation unit of the detection apparatus according to the first embodiment for an analysis image, and an example of a derivation unit deriving a positional change amount of the identification region. (A) is a conceptual diagram which shows the area | region of the analysis image in the frame before two continuous frames of an analysis image. (B) is a conceptual diagram showing a region of an analysis image in a frame after two consecutive frames of the analysis image. 図３は、実施形態１に係る検知装置が滞在検知モードで人の存在の有無を検知する際に導出部が人の動き量を導出する一例を示す概念図である。（ａ）は、本発明の実施形態１に係る連続する２つのフレームの前のフレームにおける識別領域を示す概念図である。（ｂ）は、本発明の実施形態１に係る連続する２つのフレームの後のフレームにおける識別領域を示す概念図である。FIG. 3 is a conceptual diagram illustrating an example in which the deriving unit derives the amount of human movement when the detection device according to the first embodiment detects the presence or absence of a person in the stay detection mode. (A) is a conceptual diagram which shows the identification area | region in the flame | frame before the two continuous frames which concern on Embodiment 1 of this invention. (B) is a conceptual diagram which shows the identification area | region in the frame after two continuous frames which concern on Embodiment 1 of this invention. 図４は、本発明の実施形態１に係る検知装置が、識別領域の位置変化量に基づいて検知モードを切り替えるフローチャートである。FIG. 4 is a flowchart in which the detection apparatus according to the first embodiment of the present invention switches the detection mode based on the position change amount of the identification area. 図５は、実施形態１に係る検知装置が、進入検知モードで人の存在の有無を検知するフローチャートである。FIG. 5 is a flowchart in which the detection device according to the first embodiment detects the presence or absence of a person in the approach detection mode. 図６は、実施形態１に係る検知装置が、滞在検知モードで人の存在の有無を検知するフローチャートである。FIG. 6 is a flowchart in which the detection device according to the first embodiment detects the presence or absence of a person in the stay detection mode. 図７は、実施形態２に係る検知システムのブロック図である。FIG. 7 is a block diagram of a detection system according to the second embodiment. 図８は、実施形態２に係るフィルタ画像処理の一例を示す概念図である。FIG. 8 is a conceptual diagram illustrating an example of filtered image processing according to the second embodiment. 図９は、実施形態２に係る検知装置が、滞在検知モードで人の存在の有無を検知するフローチャートである。FIG. 9 is a flowchart in which the detection device according to the second embodiment detects the presence or absence of a person in the stay detection mode.
　以下、本発明の実施の形態について、図面を用いて詳細に説明する。なお、以下で説明する実施の形態は、いずれも本発明の好ましい一具体例を示す。以下の実施の形態で示される数値、形状、材料、構成要素、構成要素の配置位置および接続形態、ステップおよびステップの順序等は、一例であり、本発明を限定する主旨ではない。また、以下の実施の形態における構成要素のうち、本発明の最上位概念を示す独立請求項に記載されていない構成要素については、より好ましい形態を構成する任意の構成要素として説明する。 Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that each of the embodiments described below shows a preferred specific example of the present invention. The numerical values, shapes, materials, constituent elements, arrangement positions and connection forms of the constituent elements, steps, the order of steps, and the like shown in the following embodiments are merely examples, and are not intended to limit the present invention. In addition, among the constituent elements in the following embodiments, constituent elements that are not described in the independent claims showing the highest concept of the present invention will be described as optional constituent elements that constitute a more preferable embodiment.
　（実施形態１）
　以下、実施形態１に係る検知装置および検知システムについて図１～図６を用いて説明する。 (Embodiment 1)
Hereinafter, the detection apparatus and the detection system according to the first embodiment will be described with reference to FIGS.
　図１は、実施形態１に係る検知システム１２０のブロック図である。図１に示すように、検知システム１２０は、検知装置１００および負荷６を備える。検知装置１００は、撮像部２と、制御部３と、人の存在の有無に応じて制御対象に対して制御信号を送信する送信部４と、記憶部５と、を備える。 FIG. 1 is a block diagram of a detection system 120 according to the first embodiment. As shown in FIG. 1, the detection system 120 includes a detection device 100 and a load 6. The detection apparatus 100 includes an imaging unit 2, a control unit 3, a transmission unit 4 that transmits a control signal to a control target in accordance with the presence or absence of a person, and a storage unit 5.
　制御部３は、撮像部２が撮像した解析画像の領域内の人の存在の有無を検知する検知部３１と、検知部３１が解析画像の領域内に人の存在があることを検知したとき、検知した人を囲む識別領域を作成する作成部３２と、人の動き量および識別領域の位置変化量を導出する導出部３３と、を備える。 The control unit 3 detects the presence or absence of a person in the area of the analysis image captured by the imaging unit 2, and when the detection unit 31 detects the presence of a person in the area of the analysis image A creating unit 32 that creates an identification region surrounding the detected person, and a deriving unit 33 that derives the amount of movement of the person and the position change amount of the identification region.
　導出部３３は、所定期間における人の動き量を導出する。また、導出部３３は、所定期間における識別領域の位置変化量を導出する。なお、説明の便宜上、上述の「所定期間」を撮像部２が撮像した解析画像の連続した２つのフレームのフレーム間隔として説明するが、その限りではなく、例えば予め設定した期間を用いてもよい。また、識別領域における人の動き量を導出する所定期間と、識別領域の位置変化量を導出する所定期間とは、同じ期間であってもよいし、異なる期間であってもよい。 The deriving unit 33 derives the amount of human movement during a predetermined period. The deriving unit 33 derives the position change amount of the identification area in a predetermined period. For convenience of explanation, the above-mentioned “predetermined period” will be described as a frame interval between two consecutive frames of the analysis image captured by the imaging unit 2, but the present invention is not limited thereto, and for example, a preset period may be used. . Further, the predetermined period for deriving the amount of human movement in the identification area and the predetermined period for deriving the position change amount of the identification area may be the same period or different periods.
　記憶部５は、評価指標とする変化量の閾値Ｉと、動き量の閾値Ｕと、動き量の閾値Ｕより小さい滞在検知の閾値Ｔと、輝度変化量の閾値Ｋと、を記憶している。以下では、閾値Ｉ、Ｕ、Ｔ、Ｋはそれぞれ、第１、第２、第３、第４の閾値と表記すこともある。 The storage unit 5 stores a change amount threshold value I as an evaluation index, a motion amount threshold value U, a stay detection threshold value T smaller than the motion amount threshold value U, and a luminance change amount threshold value K. . Hereinafter, the threshold values I, U, T, and K may be referred to as first, second, third, and fourth threshold values, respectively.
　検知部３１は、検知モードとして、解析画像の領域内における人の存在の有無を検知する進入検知モードと、識別領域内における人の動き量で人の存在の有無を検知する滞在検知モードと、を有する。 The detection unit 31 includes, as detection modes, an entry detection mode that detects the presence / absence of a person in the area of the analysis image, a stay detection mode that detects the presence / absence of a person based on the amount of movement of the person in the identification area, Have
　なお、検知部３１の進入検知モードにおける人の存在の有無の検知方法を特に限定しなく、従来の人検知の技術を用いてもよい。例えば、背景差分を用いて人の存在の有無を検知する手法でもよく、フレーム間差分を用いて解析画像の領域２１における人の動き量を導出することで人の存在の有無を検知する手法でもよい。 In addition, the detection method of the presence or absence of a person in the approach detection mode of the detection unit 31 is not particularly limited, and a conventional human detection technique may be used. For example, a technique for detecting the presence or absence of a person using background difference may be used, or a technique for detecting the presence or absence of a person by deriving the amount of movement of the person in the region 21 of the analysis image using a difference between frames. Good.
　以下、作成部３２の識別領域の作成方法と、導出部３３の人の動き量および識別領域の位置変化量の導出方法について、図２、図３を用いて説明する。 Hereinafter, a method for creating the identification area of the creation unit 32 and a method for deriving the amount of movement of the person and the position change amount of the identification area of the derivation unit 33 will be described with reference to FIGS.
　図２は、作成部３２が作成する識別領域２２の一例と、導出部３３が識別領域２２の位置変化量を導出する一例を示す概念図である。図２の（ａ）および（ｂ）は、連続する２つのフレームの解析画像の領域２１を示す図である。 FIG. 2 is a conceptual diagram showing an example of the identification region 22 created by the creation unit 32 and an example of the derivation unit 33 deriving the positional change amount of the identification region 22. FIGS. 2A and 2B are diagrams showing an analysis image region 21 of two consecutive frames.
　図２の（ａ）に示すように、作成部３２は、進入検知モードにおいて、検知部３１が人の存在があることを検知したとき、当該人の幅、高さに基づいて長方形状の識別領域２２を当該人を囲むように作成する。 As shown in FIG. 2A, when the detection unit 31 detects the presence of a person in the approach detection mode, the creation unit 32 identifies the rectangle based on the width and height of the person. A region 22 is created so as to surround the person.
　図２の（ｂ）は、図２の（ａ）の次のフレームを示しており、この場合、人が移動していることを想定するため、識別領域２２が、図２の（ａ）における識別領域２２ａから図２ｂにおける識別領域２２ｂに移動する。 FIG. 2 (b) shows the next frame of FIG. 2 (a). In this case, since it is assumed that a person is moving, the identification area 22 is shown in FIG. 2 (a). The identification area 22a moves to the identification area 22b in FIG. 2b.
　導出部３３は、識別領域２２ａの中心と２２ｂの中心との間の距離Ａを算出し、距離Ａを識別領域２２の位置変化量として導出する。 The deriving unit 33 calculates the distance A between the center of the identification area 22a and the center of 22b, and derives the distance A as a position change amount of the identification area 22.
　検知部３１は、進入検知モードにおいて、導出部３３により導出した位置変化量と、記憶部５に記憶された変化量の閾値Ｉ（つまり第１の閾値）と、を比較し、位置変化量が変化量の閾値Ｉ以上の場合、進入検知モードのままで人の存在の有無を検知し、位置変化量が変化量の閾値Ｉ未満の場合、滞在検知モードに切り替える。 In the approach detection mode, the detection unit 31 compares the position change amount derived by the deriving unit 33 with the threshold value I of the change amount stored in the storage unit 5 (that is, the first threshold value). When the change amount is equal to or greater than the threshold value I, the presence / absence of a person is detected in the approach detection mode.
　作成部３２は、人が検知装置１００の解析画像の領域内を移動するにつれて、識別領域２２の位置を更新することで、検知部が解析画像の領域内の人を追跡することができる。 The creation unit 32 updates the position of the identification region 22 as the person moves within the analysis image region of the detection apparatus 100, so that the detection unit can track the person within the analysis image region.
　　図３は、検知装置１００が滞在検知モードで人の存在の有無を検知する際に導出部３３が人の動き量を導出する一例を示す概念図である。図３の（ａ）および（ｂ）は、連続する２つのフレームの識別領域２２ｃ、２２ｄを示す図である。 FIG. 3 is a conceptual diagram illustrating an example in which the deriving unit 33 derives the amount of human movement when the detection apparatus 100 detects the presence or absence of a person in the stay detection mode. FIGS. 3A and 3B are diagrams showing identification regions 22c and 22d of two consecutive frames.
　図３に示すように、滞在検知モードにおいて、検知部３１は、識別領域２２における人の動き量に基づいて人の存在の有無を検知する。図３に示すように、人の動きが、図３の（ａ）の識別領域２２ｃから図３の（ｂ）の識別領域２２ｄに変化する際に、画素の輝度は、人の動きの変動に基いて変化する。 As shown in FIG. 3, in the stay detection mode, the detection unit 31 detects the presence or absence of a person based on the amount of movement of the person in the identification area 22. As shown in FIG. 3, when the movement of a person changes from the identification area 22c in FIG. 3A to the identification area 22d in FIG. 3B, the luminance of the pixel changes due to fluctuations in the movement of the person. Change based on.
　導出部３３は、所定期間において、識別領域２２における人の動き量を導出する。すなわち、導出部３３は、識別領域２２ｃと識別領域２２ｄとの間の画素の輝度の変化量が記憶部５に記憶された輝度変化量の閾値Ｋ（つまり第４の閾値）以上の画素の数、を人の動き量として導出する。 The deriving unit 33 derives the amount of human movement in the identification area 22 during a predetermined period. That is, the deriving unit 33 counts the number of pixels in which the luminance change amount of the pixel between the identification region 22c and the identification region 22d is equal to or larger than the threshold value K (that is, the fourth threshold value) of the luminance change amount stored in the storage unit 5. , Is derived as the amount of human movement.
　検知部３１は、滞在検知モードにおいて、導出部３３により人の動き量を導出することで、人の動き量と、記憶部５に記憶された滞在検知の閾値Ｔ（つまり第３の閾値）と、動き量の閾値Ｕ（つまり第２の閾値）と、を比較する。検知部３１は、人の動き量が閾値Ｔ以上閾値Ｕ未満であれば、人の存在があると判定する。また、検知部３１は、人の動き量が閾値Ｔ未満であれば、人の存在がないと判定する。また、検知部３１は、人の動き量が閾値Ｕ以上であれば、滞在検知モードから進入検知モードに切り替える。 In the stay detection mode, the detection unit 31 derives the amount of movement of the person by the deriving unit 33, so that the amount of movement of the person and the threshold T of stay detection stored in the storage unit 5 (that is, the third threshold) , The threshold U of motion amount (that is, the second threshold) is compared. The detection unit 31 determines that there is a person if the amount of movement of the person is greater than or equal to the threshold T and less than the threshold U. Moreover, if the amount of movement of the person is less than the threshold value T, the detection unit 31 determines that there is no person. Moreover, the detection part 31 will switch from stay detection mode to approach detection mode, if the amount of human movement is more than the threshold value U. FIG.
　負荷６は、少なくとも「点灯する」、「消灯する」の二つの動作モードを有する照明装置であると想定している。 It is assumed that the load 6 is a lighting device having at least two operation modes of “turned on” and “turned off”.
　送信部４は、負荷６が消灯する状態である場合、検知部３１が人の存在があると判定したら、検知装置１００の外部にある制御対象となる負荷６に対して点灯する制御信号を送信する。送信部４は、負荷６が「点灯する」の動作モードである場合、検知部３１が人の存在がないと判断したら、負荷６に対して「消灯する」の動作モードに切り替える制御信号を送信する。 If the detection unit 31 determines that there is a person when the load 6 is in a state where the load 6 is turned off, the transmission unit 4 transmits a control signal that is lit to the load 6 to be controlled outside the detection apparatus 100. To do. When the load unit 6 is in the “lighting” operation mode, the transmission unit 4 transmits a control signal for switching to the “lights off” operation mode when the detection unit 31 determines that no person is present. To do.
　なお、送信部４は、負荷６に対して直接的に制御信号を送信してもよく、中継器（図示しない）などを介して間接的に制御信号を送信してもよい。 In addition, the transmission part 4 may transmit a control signal directly with respect to the load 6, and may transmit a control signal indirectly via a repeater (not shown) etc.
　また、送信部４の通信方式については、例えば、Ｗｉ－Ｆｉ（Ｗｉｒｅｌｅｓｓ　Ｆｉｄｅｌｉｔｙ、登録商標）などを用いる無線通信方式、または信号線による有線通信方式などが考えられるが、特に限定しない。 The communication method of the transmission unit 4 may be, for example, a wireless communication method using Wi-Fi (Wireless Fidelity, registered trademark) or a wired communication method using a signal line, but is not particularly limited.
　以下、検知装置１００の動作フローチャートについて、図４～図６を用いて説明する。 Hereinafter, an operation flowchart of the detection apparatus 100 will be described with reference to FIGS.
　図４は、検知装置１００が、識別領域２２の位置変化量に基づいて検知モードを切り替えるフローチャートである。 FIG. 4 is a flowchart in which the detection device 100 switches the detection mode based on the position change amount of the identification region 22.
　人が検知装置１００の撮像部２が撮像した解析画像の領域内に入る前に、検知部３１は、進入検知モードで人の存在の有無を検知する（ステップＳ４１）。そこで、検知部３１は、解析画像の領域内に人の存在があることを検知したとき、導出部３３により導出された識別領域２２の位置変化量と、変化量の閾値Ｉ（つまり第１の閾値）と、を比較する（ステップＳ４２）。 Before the person enters the area of the analysis image captured by the imaging unit 2 of the detection apparatus 100, the detection unit 31 detects the presence or absence of a person in the entry detection mode (step S41). Therefore, when detecting the presence of a person in the area of the analysis image, the detecting unit 31 detects the position change amount of the identification region 22 derived by the deriving unit 33 and the change amount threshold I (that is, the first value). (Threshold) is compared (step S42).
　検知部３１は、識別領域２２の位置変化量がＩ未満であれば（ステップＳ４２のＮＯ）、ステップＳ４３に進み、検知モードを進入検知モードから滞在検知モードに切り替える。検知部３１は、識別領域２２の位置変化量がＩ以上であれば（ステップＳ４２のＹＥＳ）、ステップＳ４１に戻って、引き続き進入検知モードで人の存在の有無を検知する。 If the position change amount of the identification area 22 is less than I (NO in step S42), the detection unit 31 proceeds to step S43 and switches the detection mode from the entry detection mode to the stay detection mode. If the position change amount of the identification region 22 is I or more (YES in step S42), the detection unit 31 returns to step S41 and continues to detect the presence or absence of a person in the approach detection mode.
　ステップＳ４３において、検知部３１は、滞在検知モードで人の存在の有無を検知する。そこで、検知部３１は、導出部３３により導出された人の動き量と、動き量の閾値Ｕ（つまり第２の閾値）と、を比較する（ステップＳ４４）。 In step S43, the detection unit 31 detects the presence or absence of a person in the stay detection mode. Therefore, the detection unit 31 compares the human motion amount derived by the deriving unit 33 with the motion amount threshold value U (that is, the second threshold value) (step S44).
　人の動き量がＵ未満であれば（ステップＳ４４のＹＥＳ）、検知部３１は、引続き滞在検知モードで人の存在の有無を検知する。そうでなければ、すなわち、人の動き量がＵ以上であれば（ステップＳ４４のＮＯ）、検知部３１は、ステップＳ４１に戻って、検知モードを滞在検知モードから進入検知モードに切り替える。 If the movement amount of the person is less than U (YES in step S44), the detection unit 31 continues to detect the presence or absence of the person in the stay detection mode. Otherwise, that is, if the amount of human movement is greater than or equal to U (NO in step S44), the detection unit 31 returns to step S41 and switches the detection mode from the stay detection mode to the entry detection mode.
　図５は、検知装置１００が、進入検知モードで人の存在の有無を検知するフローチャートである。 FIG. 5 is a flowchart in which the detection device 100 detects the presence or absence of a person in the approach detection mode.
　ステップＳ５１において、検知部３１は、撮像部２が撮像した解析画像に基づいて人の存在の有無を検知する。そこで、作成部３２は、検知部３１が解析画像の領域内に人の存在があることを検知したら（ステップＳ５２のＹＥＳ）、識別領域２２を作成（ステップＳ５３）する。 In step S51, the detection unit 31 detects the presence or absence of a person based on the analysis image captured by the imaging unit 2. Therefore, when the detection unit 31 detects that a person is present in the area of the analysis image (YES in step S52), the creation unit 32 creates the identification region 22 (step S53).
　ステップＳ５２において、検知部３１は、人の存在がないことを検知したら、ステップＳ５１に戻って、引き続いて進入検知モードで人の存在の有無を検知する。 In step S52, when detecting that there is no person, the detection unit 31 returns to step S51 and subsequently detects the presence or absence of the person in the entry detection mode.
　ステップＳ５４において、検知部３１は、導出部３３により導出された識別領域２２の位置変化量と、変化量の閾値Ｉ（つまり第１の閾値）と、を比較する。 In step S54, the detection unit 31 compares the position change amount of the identification area 22 derived by the deriving unit 33 with the change amount threshold value I (that is, the first threshold value).
　位置変化量がＩ以上（ステップＳ５４のＹＥＳ）であれば、検知部３１は、ステップＳ５１に戻って、引き続いて進入検知モードで人の存在の有無を検知する。位置変化量がＩ未満（ステップＳ５４のＮＯ）であれば、検知部３１は、検知モードを進入検知モードから滞在検知モードに切り替え（ステップＳ５５）、滞在検知モードで人の存在の有無を検知する。先述のように、ステップＳ５４は、実質上にステップＳ４２と同様である。 If the position change amount is I or more (YES in step S54), the detection unit 31 returns to step S51, and subsequently detects the presence or absence of a person in the entry detection mode. If the amount of change in position is less than I (NO in step S54), detection unit 31 switches the detection mode from the entry detection mode to the stay detection mode (step S55), and detects the presence or absence of a person in the stay detection mode. . As described above, step S54 is substantially the same as step S42.
　図６は、検知装置１００が、滞在検知モードで人の存在の有無を検知するフローチャートである。 FIG. 6 is a flowchart in which the detection apparatus 100 detects the presence or absence of a person in the stay detection mode.
　ステップＳ６１において、検知部３１は、識別領域２２における解析画像に基づいて人の存在の有無を検知する。そこで、検知部３１は、導出部３３により導出された人の動き量と、滞在検知の閾値Ｔ（つまり第３の閾値）と、を比較する（ステップＳ６２）。 In step S61, the detection unit 31 detects the presence or absence of a person based on the analysis image in the identification region 22. Therefore, the detection unit 31 compares the amount of movement of the person derived by the deriving unit 33 with the threshold value T (that is, the third threshold value) for stay detection (step S62).
　検知部３１は、人の動き量がＴ未満（ステップＳ６２のＮＯ）であれば、人の存在がないと判定する（ステップＳ６４）。検知部３１は、人の動き量がＴ以上（ステップＳ６２のＹＥＳ）であれば、人の動き量と、動き量の閾値Ｕ（つまり第２の閾値）と、を比較する（ステップＳ６３）。 If the amount of movement of the person is less than T (NO in step S62), the detection unit 31 determines that there is no person (step S64). If the movement amount of the person is equal to or greater than T (YES in step S62), the detection unit 31 compares the movement amount of the person with the threshold U of the movement amount (that is, the second threshold) (step S63).
　ステップＳ６３において、人の動き量がＵ未満（ステップＳ６３のＹＥＳ）であれば、検知部３１は、人の存在があると判定し（ステップＳ６５）、引き続き滞在検知モードで人の存在の有無を検知する。人の動き量がＵ以上（ステップＳ６３のＮＯ）であれば、検知部３１は、検知モードを滞在検知モードから進入検知モードに切り替え、進入検知モードで人の存在の有無を検知する（ステップＳ６６）。 In step S63, if the amount of movement of the person is less than U (YES in step S63), the detection unit 31 determines that there is a person (step S65), and continues to check whether there is a person in the stay detection mode. Detect. If the amount of movement of the person is U or more (NO in step S63), the detection unit 31 switches the detection mode from the stay detection mode to the entry detection mode, and detects the presence or absence of a person in the entry detection mode (step S66). ).
　検知部３１は、滞在検知モードで識別領域２２内において人の存在の有無を検知する際に、進入検知モードで識別領域２２外でかつ解析画像の領域２１内において他の人の存在の有無を検知する。そのため、識別領域２２内の人以外の人が解析画像の領域２１内に進入する場合、検知部３１は、進入検知モードで当該人の存在を検知することができる。 When detecting the presence or absence of a person in the identification area 22 in the stay detection mode, the detection unit 31 detects the presence or absence of another person outside the identification area 22 and in the analysis image area 21 in the entry detection mode. Detect. Therefore, when a person other than the person in the identification area 22 enters the area 21 of the analysis image, the detection unit 31 can detect the presence of the person in the entry detection mode.
　検知システム１２０は、撮像部２と、撮像部２が撮像した解析画像の領域内の人の存在の有無を検知する検知部３１と、検知部３１が解析画像の領域２１内に人の存在があることを検知したとき、検知した人を囲む識別領域２２を作成する作成部３２と、人の動き量および識別領域２２の位置変化量を導出する導出部３３と、検知部３１が人の存在の有無の検知結果に基づいて制御信号を制御対象に送信する送信部４と、を備える検知装置１００と、制御対象となる負荷６と、を備え、検知部３１は、解析画像の領域２１内における人の存在の有無を検知する進入検知モードと、識別領域２２内における人の動き量で人の存在の有無を検知する滞在検知モードと、を有し、進入検知モードにおいて、識別領域２２の位置変化量が変化量の閾値Ｉ（つまり第１の閾値）未満の場合、進入検知モードから滞在検知モードに切り替え、滞在検知モードにおいて、人の動き量が動き量の閾値Ｕ（つまり第２の閾値）以上の場合、滞在検知モードから進入検知モードに切り替える。 The detection system 120 includes an imaging unit 2, a detection unit 31 that detects the presence / absence of a person in an analysis image area captured by the imaging unit 2, and the detection unit 31 includes a person in the analysis image area 21. When a certain thing is detected, the creation part 32 which creates the identification area 22 surrounding the detected person, the deriving part 33 for deriving the amount of movement of the person and the position change amount of the identification area 22, and the detection part 31 are the presence of the person. A detection device 100 including a transmission unit 4 that transmits a control signal to a control target based on a detection result of the presence or absence of the control signal, and a load 6 that is a control target. An entry detection mode for detecting the presence / absence of a person in the vehicle and a stay detection mode for detecting the presence / absence of a person based on the amount of movement of the person in the identification region 22. Position change amount is the threshold of change amount When it is less than I (that is, the first threshold value), the mode is switched from the approach detection mode to the stay detection mode. In the stay detection mode, when the human motion amount is equal to or greater than the motion amount threshold value U (that is, the second threshold value) Switch from mode to entry detection mode.
　上記の構成により、検知装置１００および検知システム１２０は、特許文献２に記載のものと比較すると、以下の効果を奏することができる。 With the above configuration, the detection device 100 and the detection system 120 can achieve the following effects as compared with those described in Patent Document 2.
　特許文献２に記載の画像処理装置は、検出対象の移動量や動きが大きい場合に検出対象を検出する第１の輪郭抽出手段と、検出対象の移動量や動きが比較的に小さい場合に検出対象を検出する第２の輪郭抽出手段と、検出対象が静止している場合に検出対象を検出する第３の輪郭抽出手段と、を有する。しかし、特許文献２に記載の画像処理装置は、常に第１の輪郭抽出手段～第３の輪郭抽出手段を繰り返して検出対象の存在の有無を検知するものである。例えば、検出対象が大きな動きをしていても、常に第１の輪郭抽出手段で検出対象を検知するのではなく、繰り返して、先ず検出対象が静止しているか否かを判断し、ついでに微少な動きをしているか否かを判断した後、大きな動きをしているか否かを判断するため、検知処理にかかる負荷が大きい。 The image processing apparatus described in Patent Literature 2 detects a first contour extraction unit that detects a detection target when the movement amount or movement of the detection target is large, and a detection when the movement amount or movement of the detection target is relatively small. It has the 2nd outline extraction means which detects a target, and the 3rd outline extraction means which detects a detection target, when a detection target is still. However, the image processing apparatus described in Patent Document 2 always detects the presence / absence of a detection target by repeating the first contour extraction means to the third contour extraction means. For example, even if the detection target is moving greatly, the first contour extraction means does not always detect the detection target, but it is repeatedly determined whether the detection target is stationary first, and then a slight amount is detected. Since it is determined whether or not it is moving after determining whether or not it is moving, the load on the detection process is large.
　これに対して、検知装置１００および検知システム１２０は、検知部３１が、進入検知モードにおいて、識別領域２２の位置変化量が変化量の閾値Ｉ（つまり第１の閾値）未満であれば、すなわち、人の移動量が比較的に小さい、または滞在している場合、滞在検知モードに切り替えて人の存在の有無を検知する。人の動き量が動き量の閾値Ｕ（つまり第２の閾値）以上であれば、すなわち、人の移動量が比較的に大きい場合、検知部が、滞在検知モードから進入検知モードに切り替えて人の存在の有無を検知する。それ故、特許文献２に記載の画像処理装置により、処理する量が小さいため、検知処理にかかる負荷が小さい。 On the other hand, in the detection device 100 and the detection system 120, if the detection unit 31 is less than the change amount threshold I (that is, the first threshold) in the approach detection mode, When the movement amount of the person is relatively small or staying, the presence / absence of the person is detected by switching to the stay detection mode. If the movement amount of the person is equal to or greater than the movement amount threshold U (that is, the second threshold), that is, if the movement amount of the person is relatively large, the detection unit switches from the stay detection mode to the entry detection mode. Detect the presence or absence of. Therefore, since the amount of processing by the image processing apparatus described in Patent Document 2 is small, the load on the detection process is small.
　よって、検知装置１００および検知システム１２０は、検知処理にかかる負荷が小さく、人の行動に応じて人の存在の有無を精度よく検知することができる。 Therefore, the detection device 100 and the detection system 120 have a small load on the detection process, and can accurately detect the presence or absence of a person according to a person's action.
　また、検知装置１００および検知システム１２０の検知部３１は、滞在検知モードにおいて移動量が比較的に小さい、または滞在している人を検知する際、識別領域２２における解析画像に基づいて人の存在の有無を検知することで、識別領域２２の領域外に外乱があっても、例えば鳥や猫などの動物が検知範囲内に入る場合、またはスイッチや、鏡などによる反射光が発生する場合、その影響を受けることなく移動量が比較的に小さい、または滞在している人の存在の有無を検知することができる。 In addition, when the detection unit 31 of the detection device 100 and the detection system 120 detects a person whose movement amount is relatively small or stays in the stay detection mode, the presence of a person based on the analysis image in the identification region 22 is detected. Even if there is a disturbance outside the area of the identification area 22, for example, when an animal such as a bird or a cat enters the detection range, or when reflected light from a switch or a mirror is generated, Without being affected, it is possible to detect the presence or absence of a person whose movement amount is relatively small or staying.
　また、導出部３３は、フレーム間の識別領域２２における画素の輝度の変化量が輝度変化量の閾値Ｋ（つまり第４の閾値）以上の画素の数を人の動き量として導出することで、識別領域２２における外乱により、輝度の変化量がＫ未満の画素が発生しても、検知部３１は、その影響を受けることなく人の存在の有無を検知することができる。 In addition, the deriving unit 33 derives the number of pixels in which the luminance change amount of the pixels in the identification region 22 between frames is equal to or greater than the luminance change amount threshold value K (that is, the fourth threshold value) as a human motion amount, Even if a pixel whose luminance change amount is less than K occurs due to a disturbance in the identification region 22, the detection unit 31 can detect the presence or absence of a person without being affected by the influence.
　以上により、検知装置１００および検知システム１２０は、人が検知範囲において移動量が比較的に小さい、または滞在している場合でも、人の存在の有無を精度高く、効率よく検知することができる。 As described above, the detection device 100 and the detection system 120 can detect the presence or absence of a person with high accuracy and efficiency even when the movement amount of the person is relatively small or stays within the detection range.
　なお、説明の便宜上、検知部３１、作成部３２、導出部３３が制御部３に設けられ、送信部４、記憶部５、が制御部３に外付けられるように説明しているが、設計事項なため、それに限定しない。例えば、送信部４、記憶部５を制御部３に設けてもよい。 For convenience of explanation, the detection unit 31, the creation unit 32, and the derivation unit 33 are provided in the control unit 3, and the transmission unit 4 and the storage unit 5 are externally attached to the control unit 3. Because it is a matter, it is not limited to that. For example, the transmission unit 4 and the storage unit 5 may be provided in the control unit 3.
　また、進入検知モードにおいて、撮像部２が撮像した画像の全体を解析画像の領域とするものに限らず、例えば撮像部２が撮像した画像の一部を解析画像の領域としてもよい。 In the approach detection mode, the entire image captured by the imaging unit 2 is not limited to the analysis image region, and for example, a part of the image captured by the imaging unit 2 may be used as the analysis image region.
　また、負荷６として、照明装置に限定するものではなく、例えば空調機器、調理機器等のように、少なくとも２つの動作モードを有する電気機器であればよい。 Further, the load 6 is not limited to the lighting device, and may be an electric device having at least two operation modes such as an air conditioner and a cooking device.
　また、撮像部２のフレーム間隔、すなわち、図２ａと図２ｂとの間の期間および図３ａと図３ｂとの間の期間は、例えば２００ｍｓであるが、それに限定しない。 Further, the frame interval of the imaging unit 2, that is, the period between FIG. 2a and FIG. 2b and the period between FIG. 3a and FIG. 3b are, for example, 200 ms, but are not limited thereto.
　また、導出部３３は、識別領域２２の位置変化量を導出する際に、必ずしも識別領域２２の中心を基準点とする限りではない。 Further, when the deriving unit 33 derives the amount of change in the position of the identification region 22, the deriving unit 33 is not necessarily limited to using the center of the identification region 22 as a reference point.
　また、送信部４は、検知部３１が滞在検知モードで人の存在があると判定するときと、進入検知モードで人の存在があると判定するときに、それぞれ異なる制御信号を負荷６に送信してもよい。そうすることで、人の進入、滞在に応じて負荷６を制御することができる。 The transmission unit 4 transmits different control signals to the load 6 when the detection unit 31 determines that there is a person in the stay detection mode and when it is determined that there is a person in the approach detection mode. May be. By doing so, the load 6 can be controlled according to the person's approach and stay.
　（実施形態２）
　以下、実施形態２に係る検知装置２００および検知システム２２０について図７～図９を用いて説明する。検知システム２２０は、実施形態１の検知システム１２０と比べて、制御部３が更に解析画像に画像処理を行う画像処理部３４を有する点と、滞在モードにおいて検知部３１が所定期間Ｑにわたって継続的に人の存在がないと検知したときに人の存在がないと判定する点と、で異なる。なお、実施形態１と同様の構成については、同符号を付して説明を適宜省略する。 (Embodiment 2)
Hereinafter, the detection device 200 and the detection system 220 according to the second embodiment will be described with reference to FIGS. Compared to the detection system 120 of the first embodiment, the detection system 220 has a point that the control unit 3 further includes an image processing unit 34 that performs image processing on the analysis image, and the detection unit 31 continuously operates over a predetermined period Q in the stay mode. It is different in that it is determined that there is no person when it is detected that there is no person. In addition, about the structure similar to Embodiment 1, the same code | symbol is attached | subjected and description is abbreviate | omitted suitably.
　図７は、実施形態２に係る検知システム２２０のブロック図である。図７に示すように、検知システム２２０は、検知装置２００および負荷６を備える。検知装置２００の制御部３は、更に画像処理部３４を有する。また、記憶部５は、更に期間の閾値Ｑを記憶している。 FIG. 7 is a block diagram of the detection system 220 according to the second embodiment. As shown in FIG. 7, the detection system 220 includes a detection device 200 and a load 6. The control unit 3 of the detection device 200 further includes an image processing unit 34. The storage unit 5 further stores a threshold value Q for the period.
　画像処理部３４は、撮像部２から撮像した解析画像にソーベルフィルタ画像処理を行う。 The image processing unit 34 performs Sobel filter image processing on the analysis image captured from the imaging unit 2.
　画像処理部３４は、解析画像に対して、ソーベルフィルタ画像処理を行って、その画像処理後の出力画像を検知部３１、作成部３２、導出部３３に出力する。 The image processing unit 34 performs Sobel filter image processing on the analysis image, and outputs the output image after the image processing to the detection unit 31, the creation unit 32, and the derivation unit 33.
　図８は、撮像部２から撮像した解析画像と、解析画像に対してソーベルフィルタ画像処理を適用した後の出力画像の一例を示す概念図である。 FIG. 8 is a conceptual diagram showing an example of an analysis image picked up from the image pickup unit 2 and an output image after the Sobel filter image processing is applied to the analysis image.
　図８に示すように、解析画像にソーベルフィルタ画像処理を適用することで、検知対象となる人の外郭をより精度高く検知することができる。 As shown in FIG. 8, by applying the Sobel filter image processing to the analysis image, the outline of the person to be detected can be detected with higher accuracy.
　図９は、検知装置２００が、滞在検知モードで人の存在の有無を検知するフローチャートである。 FIG. 9 is a flowchart in which the detection device 200 detects the presence or absence of a person in the stay detection mode.
　図９に示すように、検知部３１は、ステップＳ９１において、画像処理部３４による解析画像にソーベルフィルタ画像処理を適用した出力画像を取得し、その識別領域内における人の動き量で人の存在の有無を検知する。 As shown in FIG. 9, in step S91, the detection unit 31 acquires an output image obtained by applying the Sobel filter image processing to the analysis image by the image processing unit 34, and the human motion amount in the identification region Detect presence or absence.
　ステップＳ９２において、検知部３１は、導出部３３により導出された識別領域２２における人の動き量と、滞在検知の閾値Ｔと、を比較する。人の動き量が閾値Ｔ以上（ステップＳ９２のＹＥＳ）であれば、検知部３１は、人の動き量と、動き量の閾値Ｕと、を比較する（ステップＳ９５）。人の動き量が閾値Ｔ未満（ステップＳ９２のＮＯ）であれば、検知部３１は、タイムカウントを開始し、期間の閾値Ｑに経過したかどうかを判定する（ステップＳ９３）。 In step S92, the detection unit 31 compares the amount of movement of the person in the identification area 22 derived by the deriving unit 33 with the threshold value T for stay detection. If the human motion amount is equal to or greater than the threshold T (YES in step S92), the detection unit 31 compares the human motion amount with the motion amount threshold U (step S95). If the amount of human movement is less than the threshold T (NO in step S92), the detection unit 31 starts time counting and determines whether or not the period threshold Q has elapsed (step S93).
　検知部３１は、ステップＳ９３において、指定された期間Ｑにおいて継続的に人の動き量が閾値Ｔ未満である場合（ステップＳ９３のＹＥＳ）、人の存在がないと判定する（ステップＳ９４）。そうでなければ、検知部３１は、タイムカウントをリセットして引き続き滞在検知モードで人の存在の有無を検知する（ステップＳ９３のＮＯ）。 In step S93, the detection unit 31 determines that there is no person when the amount of movement of the person is continuously less than the threshold T during the designated period Q (YES in step S93) (step S94). Otherwise, the detection unit 31 resets the time count and continuously detects the presence or absence of a person in the stay detection mode (NO in step S93).
　ステップＳ９５において、人の動き量がＵ未満（ステップＳ９５のＹＥＳ）であれば、検知部３１は、人の存在があると判定し（ステップＳ９６）、引き続き滞在検知モードで当該人を追跡する。人の動き量がＵ以上（ステップＳ９５のＮＯ）であれば、検知部３１は、検知モードを滞在検知モードから進入検知モードに切り替える（ステップＳ９７）。 In step S95, if the amount of movement of the person is less than U (YES in step S95), the detection unit 31 determines that there is a person (step S96) and continues to track the person in the stay detection mode. If the movement amount of the person is U or more (NO in step S95), the detection unit 31 switches the detection mode from the stay detection mode to the entry detection mode (step S97).
　検知装置２００および検知システム２２０は、画像処理部３４により解析画像にソーベルフィルタ画像処理を適用することで、人の存在の有無をより精度高く検知することができる。 The detection device 200 and the detection system 220 can detect the presence or absence of a person with higher accuracy by applying the Sobel filter image processing to the analysis image by the image processing unit 34.
　なお、検知部３１は、滞在検知モードにおいて人の存在の有無を検知する際にフィルタ画像処理を適用した出力画像に基づいて人の存在の有無を検知すると説明しているが、その限りではなく、進入検知モードにおいて人の存在の有無を検知する際にもフィルタ画像処理を適用した出力画像を用いてもよい。 Although the detection unit 31 is described as detecting the presence / absence of a person based on an output image to which filter image processing is applied when detecting the presence / absence of a person in the stay detection mode, the present invention is not limited thereto. An output image to which filter image processing is applied may also be used when detecting the presence or absence of a person in the entry detection mode.
　また、フィルタ画像処理として、ソーベルフィルタ画像処理に限定しなく、例えば、１次微分フィルタ（例えば、エッジ検出、線検出など）、２次微分フィルタ（例えば、ラプラシアンフィルタなど）、画像強調（例えば、低周波強調、高周波強調など）などを用いてもよい。 The filter image processing is not limited to the Sobel filter image processing. For example, a primary differential filter (for example, edge detection, line detection, etc.), a secondary differential filter (for example, Laplacian filter, etc.), image enhancement (for example, , Low frequency enhancement, high frequency enhancement, etc.) may be used.
　また、画像処理部３４は、制御部３に設けるものに限定しない。例えば制御部３とは別に設けてもよい。 Further, the image processing unit 34 is not limited to that provided in the control unit 3. For example, it may be provided separately from the control unit 3.
　また、滞在モードにおいて検知部３１が所定期間Ｑにわたって継続的に人の存在がないと検知したときに人の存在がないと判定することで、滞在モードにおける人の存在の有無をより精度高く検知することができる。 Further, the presence or absence of a person in the stay mode is detected with higher accuracy by determining that there is no person when the detection unit 31 detects that there is no person continuously over the predetermined period Q in the stay mode. can do.
　なお、制御部３が解析画像に画像処理を行う画像処理部３４を有する点と、滞在モードにおいて検知部３１が所定期間Ｑにわたって継続的に人の存在がないと検知したときに人の存在がないと判定する点とは、共に採用するものに限らず、いずれか一方のみを採用するものであってもよい。 It should be noted that the control unit 3 has an image processing unit 34 that performs image processing on the analysis image, and that the presence of a person is detected when the detection unit 31 detects that no person exists continuously over a predetermined period Q in the stay mode. The point determined to be not limited is not limited to the point that is used together, but only one of them may be used.
　（実施形態３）
　以下、実施形態３に係る検知システム３２０について説明する。検知システム３２０は、実施形態２の検知システム２２０と比べて、導出部３３が滞在検知モードにおいて識別領域２２内における画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素の数と識別領域２２内における画素の数との割合を人の動き量として導出し、進入検知モードにおいて解析画像の領域２１内における画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素の数と解析画像の領域２１内における画素の数との割合を人の動き量として導出する点、で異なる。なお、実施形態２と同様の構成については、同符号を付して説明を適宜省略する。 (Embodiment 3)
Hereinafter, the detection system 320 according to the third embodiment will be described. Compared to the detection system 220 of the second embodiment, the detection system 320 includes the number of pixels in which the luminance change amount of the pixels in the identification area 22 in the stay detection mode is greater than or equal to the threshold K of the luminance change amount and the identification area. The ratio of the number of pixels in 22 is derived as the amount of human movement, and in the approach detection mode, the number of pixels in which the luminance change amount in the analysis image area 21 is equal to or greater than the threshold value K of the luminance change amount and the analysis image The difference is that the ratio of the number of pixels in the area 21 is derived as the amount of human movement. In addition, about the structure similar to Embodiment 2, the same code | symbol is attached | subjected and description is abbreviate | omitted suitably.
　検知装置３００の導出部３３は、滞在検知モードにおいて、識別領域２２内における画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素の数と識別領域２２内における画素の数との割合、を人の動き量として導出し、進入検知モードにおいて、解析画像の領域２１内における画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素の数と解析画像の領域２１内における画素の数との割合、を人の動き量として導出する。 In the stay detection mode, the deriving unit 33 of the detection device 300 has a ratio between the number of pixels whose luminance change amount in the identification region 22 is equal to or greater than the threshold value K of the luminance change amount and the number of pixels in the identification region 22; In the approach detection mode, the number of pixels whose luminance change amount in the analysis image region 21 is equal to or greater than the threshold K of luminance change amount and the number of pixels in the analysis image region 21. The ratio of the above and the amount of movement of the person is derived.
　検知装置３００および検知システム３２０の検知部３１は、進入検知モードにおいて導出部３３が導出した人の動き量と記憶部５に記憶されている進入検知の閾値Ｓと比較することで、人の存在の有無を判断する。 The detection unit 31 of the detection device 300 and the detection system 320 compares the amount of movement of the person derived by the deriving unit 33 with the threshold value S of the entry detection stored in the storage unit 5 in the entry detection mode, thereby Determine the presence or absence.
　検知装置３００および検知システム３２０の検知部３１は、滞在検知モードにおいて導出部３３が導出した人の動き量と滞在検知の閾値Ｔとを比較して、人の存在の有無を判断する。 The detection unit 31 of the detection device 300 and the detection system 320 compares the amount of movement of the person derived by the deriving unit 33 with the threshold T for detection of stay in the stay detection mode, and determines whether or not a person is present.
　なお、進入検知の閾値Ｓと、滞在検知の閾値Ｔと、関係を特に限定しない。例えば、滞在検知モードでの人の検知を厳しく設定する場合、滞在検知の閾値Ｔを進入検知の閾値Ｓより小さいように設定すればよい。 In addition, the threshold value S for entering detection and the threshold value T for stay detection are not particularly limited. For example, when the detection of a person in the stay detection mode is strictly set, the stay detection threshold T may be set to be smaller than the entry detection threshold S.
　検知装置３００および検知システム３２０の導出部３３は、滞在検知モードにおいて、識別領域２２内における画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素の数と識別領域２２内における画素の数との割合、を人の動き量として導出し、進入検知モードにおいて、解析画像の領域２１内における画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素の数と解析画像の領域２１内における画素の数との割合、を人の動き量として導出することで、解析画像の領域２１の拡大、減少に伴う解析画像の画素の数が変化しても、同じ滞在検知の閾値Ｔと、進入検知の閾値Ｓと、を用いて人の存在の有無を検知することができる。 In the stay detection mode, the deriving unit 33 of the detection device 300 and the detection system 320 includes the number of pixels whose luminance change amount in the identification area 22 is equal to or greater than the threshold value K of the luminance change amount and the number of pixels in the identification area 22. In the approach detection mode, the number of pixels whose luminance change amount in the analysis image area 21 is greater than or equal to the threshold K of the luminance change amount and the analysis image area 21 in the approach detection mode. By deriving the ratio of the number of pixels in the image as the amount of movement of the person, even if the number of pixels of the analysis image changes due to the enlargement or reduction of the area 21 of the analysis image, The presence / absence of a person can be detected using the threshold value S for detecting the entry.
　（実施形態４）
　以下、実施形態４に係る検知システム４２０について説明する。検知システム４２０は、実施の形態３の検知システム３２０と比べて、導出部３３が滞在検知モードにおいて識別領域２２内における画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素の塊の面積の大きさを人の動き量として導出し、進入検知モードにおいて解析画像の領域２１内における画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素の数と解析画像の領域２１内における画素の塊の面積の大きさを人の動き量として導出する点、で異なる。なお、実施形態２と同様の構成については、同符号を付して説明を適宜省略する。 (Embodiment 4)
Hereinafter, the detection system 420 according to the fourth embodiment will be described. Compared to the detection system 320 of the third embodiment, the detection system 420 is an area of a pixel block in which the luminance change amount of the pixel in the identification region 22 is greater than or equal to the threshold value K of the luminance change amount in the stay detection mode. Is calculated as the amount of human movement, and in the approach detection mode, the number of pixels whose luminance change amount in the analysis image area 21 is equal to or greater than the threshold K of the luminance change amount and the pixels in the analysis image area 21. The difference is that the area size of the lump is derived as the amount of human movement. In addition, about the structure similar to Embodiment 2, the same code | symbol is attached | subjected and description is abbreviate | omitted suitably.
　検知装置４００および検知システム４２０の導出部３３は、上下左右、または斜めに相隣する画素を一つの塊とする。 The deriving unit 33 of the detection device 400 and the detection system 420 sets pixels adjacent to each other vertically, horizontally, or diagonally as one lump.
　検知装置４００および検知システム４２０の導出部３３は、滞在検知モードにおいて、識別領域２２内における画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素の塊の面積の大きさを人の動き量として導出し、進入検知モードにおいて、解析画像の領域２１内における画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素の塊の面積の大きさを人の動き量として導出する。 In the stay detection mode, the deriving unit 33 of the detection device 400 and the detection system 420 determines the size of an area of a pixel block in which the luminance change amount of the pixel in the identification region 22 is equal to or greater than the threshold value K of the luminance change amount. In the approach detection mode, the size of the pixel block area in which the luminance change amount of the pixel in the region 21 of the analysis image is equal to or greater than the threshold value K of the luminance change amount is derived as the human motion amount.
　検知装置４００および検知システム４２０の導出部３３は、画素の輝度の変化量が輝度変化量の閾値Ｋ以上の画素において、当該画素の数の代わりに、当該画素の塊の面積の大きさを基準として人の動き量を導出することで、外乱による輝度が変化する画素が離散するたき、その影響を受け難くすることができる。よって、検知装置４００および検知システム４２０は、人の存在の有無をより精度高く検知することができる。 The deriving unit 33 of the detection device 400 and the detection system 420 uses the size of the block of pixels as a reference instead of the number of the pixels in the pixel whose luminance change amount is equal to or greater than the threshold value K of the luminance change amount. As described above, by deriving the amount of human motion, the pixels whose luminance changes due to disturbance are dispersed and can be made less susceptible to the influence. Therefore, the detection device 400 and the detection system 420 can detect the presence or absence of a person with higher accuracy.
　（実施形態５）
　以下、実施形態５に係る検知装置５００および検知システム５２０について説明する。検知装置５００および検知システム５２０は、検知装置２００および検知システム２２０と、導出部３３が滞在検知モードにおいて識別領域２２内における画素の輝度の変化量の標準偏差を人の動き量として導出し、進入検知モードにおいて解析画像の領域２１内における画素の輝度の変化量の標準偏差を人の動き量として導出する点、で異なる。なお、実施形態２と同様の構成については、同符号を付して説明を適宜省略する。 (Embodiment 5)
Hereinafter, the detection apparatus 500 and the detection system 520 according to the fifth embodiment will be described. The detection device 500 and the detection system 520, the detection device 200 and the detection system 220, and the deriving unit 33 derives the standard deviation of the luminance change amount of the pixel in the identification area 22 in the stay detection mode as the amount of human movement, The difference is that, in the detection mode, the standard deviation of the amount of change in luminance of the pixel in the region 21 of the analysis image is derived as the amount of human movement. In addition, about the structure similar to Embodiment 2, the same code | symbol is attached | subjected and description is abbreviate | omitted suitably.
　検知装置５００および検知システム５２０の導出部３３は、解析画像の領域２１内における画素の輝度の変化量の標準偏差を基準として人の動き量を導出することで、検知部３１は、画素の輝度の変化量のバラツキを小さくして、フレーム間差分で人の存在の有無を検知することができる。 The deriving unit 33 of the detection device 500 and the detection system 520 derives the amount of movement of the person based on the standard deviation of the change amount of the pixel luminance in the region 21 of the analysis image, so that the detection unit 31 detects the luminance of the pixel. It is possible to detect the presence / absence of a person from the difference between frames by reducing the variation in the amount of change.
　よって、検知装置５００および検知システム５２０は、人の存在の有無をより精度高く検知することができる。 Therefore, the detection device 500 and the detection system 520 can detect the presence or absence of a person with higher accuracy.
　なお、画素の輝度の変化量のバラツキを小さくするために、本実施形態で説明した標準偏差以外に、例えば、当該標準偏差のある所定期間における変化量の傾き（分散）を人の動き量として導出してもよい。 In order to reduce the variation in the amount of change in luminance of the pixels, in addition to the standard deviation described in this embodiment, for example, the slope (variance) of the amount of change during a predetermined period with the standard deviation is used as the amount of human movement. It may be derived.
　（結び）
　以上のように、本発明における技術の例示として、実施形態を説明した。そのために、添付図面および詳細な説明を提供した。 (Conclusion)
As described above, the embodiments have been described as examples of the technology in the present invention. For this purpose, the accompanying drawings and detailed description are provided.
　したがって、添付図面および詳細な説明に記載された構成要素の中には、課題解決のために必須な構成要素だけでなく、上記技術を例示するために、課題解決のためには必須でない構成要素も含まれ得る。そのため、それらの必須ではない構成要素が添付図面や詳細な説明に記載されていることをもって、直ちに、それらの必須ではない構成要素が必須であるとの認定をするべきではない。 Accordingly, among the components described in the accompanying drawings and the detailed description, not only the components essential for solving the problem, but also the components not essential for solving the problem in order to illustrate the above technique. May also be included. Therefore, it should not be immediately recognized that these non-essential components are essential as those non-essential components are described in the accompanying drawings and detailed description.
　また、上述の実施形態は、本発明における技術を例示するためのものであるから、請求の範囲またはその均等の範囲において種々の変更、置き換え、付加、省略などを行うことができる。 In addition, since the above-described embodiment is for exemplifying the technique in the present invention, various modifications, replacements, additions, omissions, and the like can be performed within the scope of the claims or an equivalent scope thereof.
１００、２００、３００、４００、５００　検知装置
１２０、２２０、３２０、４２０、５２０　検知システム
２　撮像部
２１　解析画像の領域
２２、２２ａ、２２ｂ、２２ｃ、２２ｄ　識別領域
３　制御部
３１　検知部
３２　作成部
３３　導出部
３４　画像処理部
４　送信部
５　記憶部
６　負荷 100, 200, 300, 400, 500 Detection device 120, 220, 320, 420, 520 Detection system 2 Imaging unit 21 Analysis image regions 22, 22a, 22b, 22c, 22d Identification region 3 Control unit 31 Detection unit 32 Creation unit 33 Deriving unit 34 Image processing unit 4 Transmitting unit 5 Storage unit 6 Load

Claims (11)

  1. 　撮像部と、
    　前記撮像部が撮像した解析画像の領域内の人の存在の有無を検知する検知部と、
    　前記検知部が前記解析画像の領域内に人の存在があることを検知したとき、検知した人を囲む識別領域を作成する作成部と、
    　人の動き量および前記識別領域の位置変化量を導出する導出部と、を備え、
    　前記検知部は、
    　前記解析画像の領域内における人の存在の有無を検知する進入検知モードと、
    　前記識別領域内における前記人の動き量で人の存在の有無を検知する滞在検知モードと、を有し、
    　前記進入検知モードにおいて、前記位置変化量が第１の閾値未満の場合、前記進入検知モードから前記滞在検知モードに切り替え、
    　前記滞在検知モードにおいて、前記人の動き量が第２の閾値以上の場合、前記滞在検知モードから前記進入検知モードに切り替える
    　ことを特徴とする検知装置。     An imaging unit;
    A detection unit for detecting the presence or absence of a person in the region of the analysis image captured by the imaging unit;
    When the detection unit detects that there is a person in the region of the analysis image, a creation unit that creates an identification region surrounding the detected person;
    A derivation unit for deriving the amount of movement of the person and the position change amount of the identification region,
    The detector is
    An entry detection mode for detecting the presence or absence of a person in the region of the analysis image;
    A stay detection mode for detecting the presence or absence of a person by the amount of movement of the person in the identification area, and
    In the approach detection mode, when the position change amount is less than a first threshold, switch from the approach detection mode to the stay detection mode,
    In the stay detection mode, when the amount of movement of the person is equal to or greater than a second threshold value, the detection device is switched from the stay detection mode to the entry detection mode.
  2. 　前記検知部は、
    　前記滞在検知モードにおいて、
    　前記人の動き量が前記第２の閾値より小さい第３の閾値未満であれば、人の存在がないと判定し、
    　前記人の動き量が前記第３の閾値以上、前記第２の閾値未満であれば、人の存在があると判定する
    　ことを特徴とする請求項１記載の検知装置。     The detector is
    In the stay detection mode,
    If the movement amount of the person is less than a third threshold value that is smaller than the second threshold value, it is determined that there is no person,
    The detection device according to claim 1, wherein if the amount of movement of the person is equal to or greater than the third threshold and less than the second threshold, it is determined that there is a person.
  3. 　前記検知部は、
    　少なくとも前記滞在検知モードにおいて、前記解析画像にフィルタ画像処理を適用した出力画像を用いて人の存在の有無を検知する
    　ことを特徴とする請求項１又は２に記載の検知装置。     The detector is
    3. The detection device according to claim 1, wherein presence of a person is detected using an output image obtained by applying filter image processing to the analysis image at least in the stay detection mode.
  4. 　前記フィルタ画像処理は、微分フィルタ画像処理を用いる
    　ことを特徴とする請求項３に記載の検知装置。     The detection apparatus according to claim 3, wherein the filter image processing uses differential filter image processing.
  5. 　前記導出部は、
    　前記人の動き量を、前記識別領域内における画素の輝度の変化量が第４の閾値以上の画素の数に基づいて導出する
    　ことを特徴とする請求項１～４の何れか１項に記載の検知装置。     The derivation unit includes:
    The amount of movement of the person is derived based on the number of pixels in which the amount of change in luminance of the pixels in the identification area is equal to or greater than a fourth threshold value. Detection device.
  6. 　前記導出部は、
    　前記人の動き量を、前記識別領域内における画素の輝度の変化量が第４の閾値以上の画素の数と、前記識別領域内における画素の数と、の割合に基づいて導出する
    　ことを特徴とする請求項１～４の何れか１項に記載の検知装置。     The derivation unit includes:
    The amount of movement of the person is derived based on a ratio between the number of pixels in which the amount of change in luminance of the pixels in the identification area is equal to or greater than a fourth threshold and the number of pixels in the identification area. The detection device according to any one of claims 1 to 4.
  7. 　前記導出部は、
    　前記人の動き量を、前記識別領域内における画素の輝度の変化量が第４の閾値以上の画素の塊の面積の大きさに基づいて導出する
    　ことを特徴とする請求項１～４の何れか１項に記載の検知装置。     The derivation unit includes:
    The amount of movement of the person is derived based on the size of the area of a block of pixels in which the amount of change in luminance of the pixel in the identification region is equal to or greater than a fourth threshold value. The detection device according to claim 1.
  8. 　前記導出部は、
    　前記人の動き量を、前記識別領域内における画素の輝度の変化量の標準偏差に基づいて導出する
    　ことを特徴とする請求項１～４の何れか１項に記載の検知装置。     The derivation unit includes:
    The detection device according to any one of claims 1 to 4, wherein the movement amount of the person is derived based on a standard deviation of a change amount of luminance of a pixel in the identification region.
  9. 　前記導出部は、
    　前記人の動き量を、前記識別領域内における画素の輝度の変化量の標準偏差の変化量の傾きに基づいて導出する
    　ことを特徴とする請求項１～４の何れか１項に記載の検知装置。     The derivation unit includes:
    The detection according to any one of claims 1 to 4, wherein the movement amount of the person is derived based on a slope of a change amount of a standard deviation of a change amount of luminance of a pixel in the identification region. apparatus.
  10. 　更に、前記検知部による人の存在の有無の検知結果に基づいて制御信号を制御対象に送信する送信部を備える
    　ことを特徴とする請求項１～９の何れか１項に記載の検知装置。     The detection device according to any one of claims 1 to 9, further comprising a transmission unit that transmits a control signal to a control target based on a detection result of the presence or absence of a person by the detection unit.
  11. 　撮像部と、
    　前記撮像部が撮像した解析画像の領域内の人の存在の有無を検知する検知部と、
    　前記検知部が前記解析画像の領域内に人の存在があることを検知したとき、検知した人を囲む識別領域を作成する作成部と、
    　人の動き量および前記識別領域の位置変化量を導出する導出部と、
    　前記検知部による人の存在の有無の検知結果に基づいて制御信号を制御対象に送信する送信部と、を有する検知装置と、
    　前記制御対象となる負荷と、を備え、
    　前記検知部は、
    　前記解析画像の領域内における人の存在の有無を検知する進入検知モードと、
    　前記識別領域内における前記人の動き量で人の存在の有無を検知する滞在検知モードと、を有し、
    　前記進入検知モードにおいて、前記位置変化量が第１の閾値未満の場合、前記進入検知モードから前記滞在検知モードに切り替え、
    　前記滞在検知モードにおいて、前記人の動き量が第２の閾値以上の場合、前記滞在検知モードから前記進入検知モードに切り替える
    　ことを特徴とする検知システム。     An imaging unit;
    A detection unit for detecting the presence or absence of a person in the region of the analysis image captured by the imaging unit;
    When the detection unit detects that there is a person in the region of the analysis image, a creation unit that creates an identification region surrounding the detected person;
    A deriving unit for deriving the amount of movement of the person and the position change amount of the identification region;
    A detection unit comprising: a transmission unit that transmits a control signal to a control target based on a detection result of the presence or absence of a person by the detection unit;
    A load to be controlled,
    The detector is
    An entry detection mode for detecting the presence or absence of a person in the region of the analysis image;
    A stay detection mode for detecting the presence or absence of a person by the amount of movement of the person in the identification area, and
    In the approach detection mode, when the position change amount is less than a first threshold, switch from the approach detection mode to the stay detection mode,
    In the stay detection mode, when the amount of movement of the person is greater than or equal to a second threshold, the detection system is switched from the stay detection mode to the entry detection mode.
PCT/JP2015/003586 2014-08-21 2015-07-16 Detection device and detection system WO2016027410A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2014-168151 2014-08-21
JP2014168151 2014-08-21

Publications (1)

Publication Number Publication Date
WO2016027410A1 true WO2016027410A1 (en) 2016-02-25

Family

ID=55350383

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2015/003586 WO2016027410A1 (en) 2014-08-21 2015-07-16 Detection device and detection system

Country Status (2)

Country Link
TW (1) TW201614596A (en)
WO (1) WO2016027410A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018036481A1 (en) * 2016-08-23 2018-03-01 华为技术有限公司 Method, device, and system for detecting scene change frame
US20190156508A1 (en) * 2016-03-30 2019-05-23 Nec Corporation Analysis apparatus, analysis method, and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000348268A (en) * 1999-06-07 2000-12-15 Mitsubishi Electric Corp Human body detecting device
JP2004295416A (en) * 2003-03-26 2004-10-21 Matsushita Electric Works Ltd Image processing apparatus
JP2012133759A (en) * 2010-11-29 2012-07-12 Canon Inc Object tracking device capable of detecting intrusion object, object tracking method, and storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000348268A (en) * 1999-06-07 2000-12-15 Mitsubishi Electric Corp Human body detecting device
JP2004295416A (en) * 2003-03-26 2004-10-21 Matsushita Electric Works Ltd Image processing apparatus
JP2012133759A (en) * 2010-11-29 2012-07-12 Canon Inc Object tracking device capable of detecting intrusion object, object tracking method, and storage medium

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190156508A1 (en) * 2016-03-30 2019-05-23 Nec Corporation Analysis apparatus, analysis method, and storage medium
US11094076B2 (en) 2016-03-30 2021-08-17 Nec Corporation Analysis apparatus, analysis method, and storage medium
US11176698B2 (en) 2016-03-30 2021-11-16 Nec Corporation Analysis apparatus, analysis method, and storage medium
WO2018036481A1 (en) * 2016-08-23 2018-03-01 华为技术有限公司 Method, device, and system for detecting scene change frame
CN107770538A (en) * 2016-08-23 2018-03-06 华为技术有限公司 A kind of methods, devices and systems for detecting scene switch frame
CN107770538B (en) * 2016-08-23 2020-09-11 华为技术有限公司 Method, device and system for detecting scene switching frame
US10917643B2 (en) 2016-08-23 2021-02-09 Huawei Technologies Co., Ltd. Method and apparatus for detecting scene change frame and system

Also Published As

Publication number Publication date
TW201614596A (en) 2016-04-16

Similar Documents

Publication Publication Date Title
US10509961B2 (en) Blindman navigation method and blindman navigation apparatus
CN104364824A (en) Object detection device
CN104038666B (en) A kind of video shelter detection method and device
US10863090B2 (en) Control apparatus, image capturing apparatus, control method, and computer-readable storage medium
JP2014017114A (en) Illumination system
US10094769B2 (en) Substance detection sensor, substance detecting method, and substance detection system having dual light source with optical scanning
JP6555617B2 (en) Human detection system
KR20180012613A (en) Control center system of working environment for smart factory
JP6664106B2 (en) Detection device, detection system, and program
WO2016027410A1 (en) Detection device and detection system
JP2015120584A (en) Image monitoring device and elevator monitoring device
JP2016179887A (en) Elevator in-car monitoring device
JP7021652B2 (en) In-car monitoring device
WO2019202969A1 (en) Recognition device, recognition method, and recognition program
WO2021215116A1 (en) Image recognition device and image recognition method
JP2017005485A (en) Picture monitoring device and picture monitoring method
JP2019040389A (en) Obstacle detection device, obstacle detection method, and obstacle detection program
JP2019041248A (en) Obstacle detection device, obstacle detection method, and obstacle detection program
KR102107137B1 (en) Method and Apparatus for Detecting Event by Using Pan-Tilt-Zoom Camera
JP5179132B2 (en) Human body detection device
JP2019047164A (en) Object detection system, program and object detection method
JP2016111539A (en) Lighting state determination device, lighting state determination method, and lighting state determination program
US9854204B2 (en) Communication system and method for controlling the same
JP5265265B2 (en) Automatic lighting control lighting system
JP2019003558A (en) Object detection device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15834011

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15834011

Country of ref document: EP

Kind code of ref document: A1